The present paper aims to analyze and explore the ROC632 package, specifying its main characteristics and functions. More specifically, the goal of this study is the evaluation of the effectiveness of the package and its strengths and weaknesses. This package was created in order to overcome the lack of information concerning incomplete time-to-event data, adapting the 0.632+ bootstrap estimator for the evaluation of time dependent ROC curves. By applying this package to a specific dataset (DLBCLpatients), it becomes possible to assess tangible data, determining if it is able to analyze complete and incomplete data efficiently and without bias.
展开▼
